[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85807-en":3,"doc-seo-85807-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85807,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data","Tabular learning still relies heavily on gradient-boosted decision trees, yet deep tabular models face major barriers on large-scale data caused by memory demands, high dimensionality, and many target classes. TabLoRA introduces a parameter-efficient trainable neural ensemble that shares a common backbone across predictors while applying predictor-specific low-rank adaptations. This enables ensemble-style prediction without duplicating full parameters, improving practicality under constrained resources and maintaining much of the benefits of full ensembles. ","arXiv :2607 . 10077v 1 [ cs .LG] 11 Jul 2026  \nTabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data  \nJiaqi Luoa , Shixin Xub,∗  \na School of Mathematical Sciences, Soochow University, No.1 Shizi  \nStreet, Suzhou, 215006, Jiangsu Province, China  \nb Digital innovation research center, Duke Kunshan University, No. 8 Duke  \nAvenue, Kunshan, 215000, Jiangsu Province, China  \nAbstract  \nTabular learning is still dominated by gradient-boosted decision trees (GBDTs), while recent deep learning approaches have become increasingly competitive. However, applying deep tabular models to large-scale datasets remains challenging, as large sample sizes, high feature dimensionality, or many target classes can introduce substantial computational cost. We propose TabLoRA, a parameter-efficient trainable neural ensemble for largescale tabular learning. Instead of using fully independent ensemble backbones, TabLoRA shares a common backbone across predictors and introduces predictor-specific low-rank adaptations, enabling ensemble-style prediction without full parameter duplication. Across benchmarks, TabLoRA achieves a favorable balance between predictive performance and practical efficiency compared with GBDT methods and recent deep learning baselines under the same resource constraints. Memory analysis and ablation stud-  \n∗ Corresponding author  \nEmail addresses: [jqluo@suda.edu.cn](jqluo@suda.edu.cn) (Jiaqi Luo), [sx59@duke.edu](sx59@duke.edu) (Shixin Xu )  \nies further show that the proposed design improves the feasibility of neural ensemble learning while preserving much of the benefit of full ensembles. Keywords: Large-scale Tabular Data, Deep Learning, Low-Rank Adaptation, Ensemble, Parameter-Efficient  \n1. Introduction  \nTabular data remains a fundamental modality in real-world machine learning applications [1] . Historically, gradient-boosted decision trees (GBDTs)[2 , 3 , 4] have long dominated this domain due to their strong empirical performance and robustness [5 , 6 , 7] . Recently, however, tabular deep learning has become increasingly competitive. In particular, in-context learning methods such as TabPFN [8 , 9 , 10] demonstrate that deep learning models can match or even outperform GBDT on small-and medium-scale datasets when properly formulated.  \nDespite this progress, large-scale tabular learning remains computationally challenging. Here, large-scale datasets refer to settings where scale mayarise from a large number of samples, high feature dimensionality, or many target classes. In these regimes, GBDTs become bottlenecked by tree construction, split search, and class-wise modeling costs, while deep learning models suffer from prohibitive memory and computational footprints during training, making these methods costly or even infeasible.  \nAmong deep learning approaches, MLP-based models provide a simple and computationally efficient foundation, making them naturally amenable  \nto large-scale settings. Recent work further shows that incorporating classical machine learning structures [11 , 12 , 13] can significantly enhance their performance. Compared to more complex architectures, such designs offer practical efficiency and are easier to scale to large datasets.  \nHowever, even within this design space, a fundamental challenge remains. Highly expressive MLP-based models often incur substantial memory overhead that grows with feature dimensionality and dataset size, while memoryefficient designs tend to suffer from limited representation capacity. This reveals an inherent trade-off between scalability and expressivity in largescale tabular learning, which remains insufficiently addressed by existing approaches.  \nTo overcome this limitation, we propose TabLoRA, a parameter-efficient ensemble framework that combines shared backbone learning with predictorspecific low-rank adaptations. Each predictor is modeled as a low-rank perturbation of shared weights, allowing the model to approximate the b","cbCairER7cjevFNc","https://ap.wps.com/l/cbCairER7cjevFNc","pdf",651168,1,42,"English","en",105,"# Introduction\n## Related Work\n### Deep Learning for Tabular Data\n### MLP-based Architectures","[{\"question\":\"What problem does TabLoRA address in large-scale tabular learning?\",\"answer\":\"It targets the computational difficulty of applying deep tabular models to large-scale datasets, where memory costs, feature dimensionality, and class-wise modeling can make training expensive or infeasible.\"},{\"question\":\"How does TabLoRA achieve an ensemble effect without full parameter duplication?\",\"answer\":\"TabLoRA shares a common backbone across predictors and adds predictor-specific low-rank adaptations, allowing specialization while avoiding linear growth in memory cost.\"},{\"question\":\"What evidence is provided that TabLoRA improves performance and efficiency?\",\"answer\":\"Benchmarks report a favorable balance between predictive performance and practical efficiency versus GBDT and recent deep baselines under the same resource constraints, with memory analysis and ablations supporting the design.\"}]",1784206373,106,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"tablora-parameter-efficient-low-rank-ensemble-learning-for-large-scale-tabular-data","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/tablora-parameter-efficient-low-rank-ensemble-learning-for-large-scale-tabular-data/85807/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does TabLoRA address in large-scale tabular learning?","Question",{"text":74,"@type":75},"It targets the computational difficulty of applying deep tabular models to large-scale datasets, where memory costs, feature dimensionality, and class-wise modeling can make training expensive or infeasible.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does TabLoRA achieve an ensemble effect without full parameter duplication?",{"text":79,"@type":75},"TabLoRA shares a common backbone across predictors and adds predictor-specific low-rank adaptations, allowing specialization while avoiding linear growth in memory cost.",{"name":81,"@type":72,"acceptedAnswer":82},"What evidence is provided that TabLoRA improves performance and efficiency?",{"text":83,"@type":75},"Benchmarks report a favorable balance between predictive performance and practical efficiency versus GBDT and recent deep baselines under the same resource constraints, with memory analysis and ablations supporting the design.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]